linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
	vbabka@suse.cz, hannes@cmpxchg.org, mgorman@techsingularity.net,
	dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
	peterz@infradead.org, ldufour@linux.ibm.com, paulmck@kernel.org,
	mingo@redhat.com, will@kernel.org, luto@kernel.org,
	songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
	dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
	kent.overstreet@linux.dev, punit.agrawal@bytedance.com,
	lstoakes@gmail.com, peterjung1337@gmail.com, rientjes@google.com,
	chriscli@google.com, axelrasmussen@google.com, joelaf@google.com,
	minchan@google.com, rppt@kernel.org, jannh@google.com,
	shakeelb@google.com, tatashin@google.com, edumazet@google.com,
	gthelen@google.com, gurua@google.com, arjunroy@google.com,
	soheil@google.com, leewalsh@google.com, posk@google.com,
	michalechner92@googlemail.com, linux-mm@kvack.org,
	linux-arm-kernel@lists.infradead.org,
	linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
	linux-kernel@vger.kernel.org, kernel-team@android.com,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Suren Baghdasaryan <surenb@google.com>
Subject: [PATCH v3 05/35] maple_tree: Fix write memory barrier of nodes once dead for RCU mode
Date: Wed, 15 Feb 2023 21:17:20 -0800	[thread overview]
Message-ID: <20230216051750.3125598-6-surenb@google.com> (raw)
In-Reply-To: <20230216051750.3125598-1-surenb@google.com>

From: "Liam R. Howlett" <Liam.Howlett@oracle.com>

During the development of the maple tree, the strategy of freeing
multiple nodes changed and, in the process, the pivots were reused to
store pointers to dead nodes.  To ensure the readers see accurate
pivots, the writers need to mark the nodes as dead and call smp_wmb() to
ensure any readers can identify the node as dead before using the pivot
values.

There were two places where the old method of marking the node as dead
without smp_wmb() were being used, which resulted in RCU readers seeing
the wrong pivot value before seeing the node was dead.  Fix this race
condition by using mte_set_node_dead() which has the smp_wmb() call to
ensure the race is closed.

Add a WARN_ON() to the ma_free_rcu() call to ensure all nodes being
freed are marked as dead to ensure there are no other call paths besides
the two updated paths.

This is necessary for the RCU mode of the maple tree.

Fixes: 54a611b60590 ("Maple Tree: add new data structure")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 lib/maple_tree.c                 |  7 +++++--
 tools/testing/radix-tree/maple.c | 16 ++++++++++++++++
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 3d5ab02f981a..6b6eddadd9d2 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -185,7 +185,7 @@ static void mt_free_rcu(struct rcu_head *head)
  */
 static void ma_free_rcu(struct maple_node *node)
 {
-	node->parent = ma_parent_ptr(node);
+	WARN_ON(node->parent != ma_parent_ptr(node));
 	call_rcu(&node->rcu, mt_free_rcu);
 }
 
@@ -1778,8 +1778,10 @@ static inline void mas_replace(struct ma_state *mas, bool advanced)
 		rcu_assign_pointer(slots[offset], mas->node);
 	}
 
-	if (!advanced)
+	if (!advanced) {
+		mte_set_node_dead(old_enode);
 		mas_free(mas, old_enode);
+	}
 }
 
 /*
@@ -4218,6 +4220,7 @@ static inline bool mas_wr_node_store(struct ma_wr_state *wr_mas)
 done:
 	mas_leaf_set_meta(mas, newnode, dst_pivots, maple_leaf_64, new_end);
 	if (in_rcu) {
+		mte_set_node_dead(mas->node);
 		mas->node = mt_mk_node(newnode, wr_mas->type);
 		mas_replace(mas, false);
 	} else {
diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index 958ee9bdb316..4c89ff333f6f 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -108,6 +108,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 	MT_BUG_ON(mt, mn->slot[1] != NULL);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 
+	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
 	mas.node = MAS_START;
 	mas_nomem(&mas, GFP_KERNEL);
@@ -160,6 +161,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 		MT_BUG_ON(mt, mas_allocated(&mas) != i);
 		MT_BUG_ON(mt, !mn);
 		MT_BUG_ON(mt, not_empty(mn));
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 	}
 
@@ -192,6 +194,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 		MT_BUG_ON(mt, not_empty(mn));
 		MT_BUG_ON(mt, mas_allocated(&mas) != i - 1);
 		MT_BUG_ON(mt, !mn);
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 	}
 
@@ -210,6 +213,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 			mn = mas_pop_node(&mas);
 			MT_BUG_ON(mt, not_empty(mn));
 			MT_BUG_ON(mt, mas_allocated(&mas) != j - 1);
+			mn->parent = ma_parent_ptr(mn);
 			ma_free_rcu(mn);
 		}
 		MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -233,6 +237,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 			MT_BUG_ON(mt, mas_allocated(&mas) != i - j);
 			mn = mas_pop_node(&mas);
 			MT_BUG_ON(mt, not_empty(mn));
+			mn->parent = ma_parent_ptr(mn);
 			ma_free_rcu(mn);
 			MT_BUG_ON(mt, mas_allocated(&mas) != i - j - 1);
 		}
@@ -269,6 +274,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 			mn = mas_pop_node(&mas); /* get the next node. */
 			MT_BUG_ON(mt, mn == NULL);
 			MT_BUG_ON(mt, not_empty(mn));
+			mn->parent = ma_parent_ptr(mn);
 			ma_free_rcu(mn);
 		}
 		MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -294,6 +300,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 			mn = mas_pop_node(&mas2); /* get the next node. */
 			MT_BUG_ON(mt, mn == NULL);
 			MT_BUG_ON(mt, not_empty(mn));
+			mn->parent = ma_parent_ptr(mn);
 			ma_free_rcu(mn);
 		}
 		MT_BUG_ON(mt, mas_allocated(&mas2) != 0);
@@ -334,10 +341,12 @@ static noinline void check_new_node(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_allocated(&mas) != MAPLE_ALLOC_SLOTS + 2);
 	mn = mas_pop_node(&mas);
 	MT_BUG_ON(mt, not_empty(mn));
+	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
 	for (i = 1; i <= MAPLE_ALLOC_SLOTS + 1; i++) {
 		mn = mas_pop_node(&mas);
 		MT_BUG_ON(mt, not_empty(mn));
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 	}
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
@@ -375,6 +384,7 @@ static noinline void check_new_node(struct maple_tree *mt)
 		mas_node_count(&mas, i); /* Request */
 		mas_nomem(&mas, GFP_KERNEL); /* Fill request */
 		mn = mas_pop_node(&mas); /* get the next node. */
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 		mas_destroy(&mas);
 
@@ -382,10 +392,13 @@ static noinline void check_new_node(struct maple_tree *mt)
 		mas_node_count(&mas, i); /* Request */
 		mas_nomem(&mas, GFP_KERNEL); /* Fill request */
 		mn = mas_pop_node(&mas); /* get the next node. */
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 		mn = mas_pop_node(&mas); /* get the next node. */
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 		mn = mas_pop_node(&mas); /* get the next node. */
+		mn->parent = ma_parent_ptr(mn);
 		ma_free_rcu(mn);
 		mas_destroy(&mas);
 	}
@@ -35369,6 +35382,7 @@ static noinline void check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, allocated != 1 + height * 3);
 	mn = mas_pop_node(&mas);
 	MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1);
+	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
 	MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0);
 	mas_destroy(&mas);
@@ -35386,6 +35400,7 @@ static noinline void check_prealloc(struct maple_tree *mt)
 	mas_destroy(&mas);
 	allocated = mas_allocated(&mas);
 	MT_BUG_ON(mt, allocated != 0);
+	mn->parent = ma_parent_ptr(mn);
 	ma_free_rcu(mn);
 
 	MT_BUG_ON(mt, mas_preallocate(&mas, GFP_KERNEL) != 0);
@@ -35756,6 +35771,7 @@ void farmer_tests(void)
 	tree.ma_root = mt_mk_node(node, maple_leaf_64);
 	mt_dump(&tree);
 
+	node->parent = ma_parent_ptr(node);
 	ma_free_rcu(node);
 
 	/* Check things that will make lockdep angry */
-- 
2.39.1


  parent reply	other threads:[~2023-02-16  5:18 UTC|newest]

Thread overview: 67+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-02-16  5:17 [PATCH v3 00/35] Per-VMA locks Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 01/35] maple_tree: Be more cautious about dead nodes Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 02/35] maple_tree: Detect dead nodes in mas_start() Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 03/35] maple_tree: Fix freeing of nodes in rcu mode Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 04/35] maple_tree: remove extra smp_wmb() from mas_dead_leaves() Suren Baghdasaryan
2023-02-16  5:17 ` Suren Baghdasaryan [this message]
2023-02-16  5:17 ` [PATCH v3 06/35] maple_tree: Add smp_rmb() to dead node detection Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 07/35] maple_tree: Add RCU lock checking to rcu callback functions Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 08/35] mm: Enable maple tree RCU mode by default Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 09/35] mm: introduce CONFIG_PER_VMA_LOCK Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 10/35] mm: rcu safe VMA freeing Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 11/35] mm: move mmap_lock assert function definitions Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 12/35] mm: add per-VMA lock and helper functions to control it Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 13/35] mm: mark VMA as being written when changing vm_flags Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 14/35] mm/mmap: move VMA locking before vma_adjust_trans_huge call Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 15/35] mm/khugepaged: write-lock VMA while collapsing a huge page Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 16/35] mm/mmap: write-lock VMAs before merging, splitting or expanding them Suren Baghdasaryan
2023-02-23 14:51   ` Hyeonggon Yoo
2023-02-23 14:59     ` Hyeonggon Yoo
2023-02-23 17:46     ` Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 17/35] mm/mmap: write-lock VMA before shrinking or expanding it Suren Baghdasaryan
2023-02-23 20:20   ` Liam R. Howlett
2023-02-23 20:28     ` Liam R. Howlett
2023-02-23 21:16       ` Suren Baghdasaryan
2023-02-24  1:46         ` Liam R. Howlett
2023-02-24  2:06           ` Suren Baghdasaryan
2023-02-24 16:14             ` Liam R. Howlett
2023-02-24 16:19               ` Suren Baghdasaryan
2023-02-27 17:33                 ` Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 18/35] mm/mremap: write-lock VMA while remapping it to a new address range Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 19/35] mm: write-lock VMAs before removing them from VMA tree Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 20/35] mm: conditionally write-lock VMA in free_pgtables Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 21/35] mm/mmap: write-lock adjacent VMAs if they can grow into unmapped area Suren Baghdasaryan
2023-02-16 15:34   ` Liam R. Howlett
2023-02-16 19:36     ` Suren Baghdasaryan
2023-02-17 14:50       ` Liam R. Howlett
2023-02-17 15:54         ` Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 22/35] kernel/fork: assert no VMA readers during its destruction Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 23/35] mm/mmap: prevent pagefault handler from racing with mmu_notifier registration Suren Baghdasaryan
2023-02-23 20:06   ` Liam R. Howlett
2023-02-23 20:29     ` Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 24/35] mm: introduce vma detached flag Suren Baghdasaryan
2023-02-23 20:08   ` Liam R. Howlett
2023-02-23 20:34     ` Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 25/35] mm: introduce lock_vma_under_rcu to be used from arch-specific code Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 26/35] mm: fall back to mmap_lock if vma->anon_vma is not yet set Suren Baghdasaryan
2023-02-16 15:44   ` Matthew Wilcox
2023-02-16 19:43     ` Suren Baghdasaryan
2023-02-17  2:14       ` Suren Baghdasaryan
2023-02-17 10:21         ` Hyeonggon Yoo
2023-02-17 16:13           ` Suren Baghdasaryan
2023-02-17 18:49             ` Hyeonggon Yoo
2023-02-17 16:05         ` Matthew Wilcox
2023-02-17 16:10           ` Suren Baghdasaryan
2023-04-03 19:49             ` Matthew Wilcox
2023-02-16  5:17 ` [PATCH v3 27/35] mm: add FAULT_FLAG_VMA_LOCK flag Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 28/35] mm: prevent do_swap_page from handling page faults under VMA lock Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 29/35] mm: prevent userfaults to be handled under per-vma lock Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 30/35] mm: introduce per-VMA lock statistics Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 31/35] x86/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 32/35] arm64/mm: " Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 33/35] powerc/mm: " Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 34/35] mm/mmap: free vm_area_struct without call_rcu in exit_mmap Suren Baghdasaryan
2023-02-16  5:17 ` [PATCH v3 35/35] mm: separate vma->lock from vm_area_struct Suren Baghdasaryan
2023-02-24  9:21 ` [PATCH v3 00/35] Per-VMA locks freak07
2023-02-27 16:50   ` Davidlohr Bueso
2023-02-27 17:22     ` Suren Baghdasaryan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20230216051750.3125598-6-surenb@google.com \
    --to=surenb@google.com \
    --cc=akpm@linux-foundation.org \
    --cc=arjunroy@google.com \
    --cc=axelrasmussen@google.com \
    --cc=bigeasy@linutronix.de \
    --cc=chriscli@google.com \
    --cc=dave@stgolabs.net \
    --cc=david@redhat.com \
    --cc=dhowells@redhat.com \
    --cc=edumazet@google.com \
    --cc=gthelen@google.com \
    --cc=gurua@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hughd@google.com \
    --cc=jannh@google.com \
    --cc=jglisse@google.com \
    --cc=joelaf@google.com \
    --cc=kent.overstreet@linux.dev \
    --cc=kernel-team@android.com \
    --cc=ldufour@linux.ibm.com \
    --cc=leewalsh@google.com \
    --cc=liam.howlett@oracle.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linuxppc-dev@lists.ozlabs.org \
    --cc=lstoakes@gmail.com \
    --cc=luto@kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=michalechner92@googlemail.com \
    --cc=michel@lespinasse.org \
    --cc=minchan@google.com \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=peterjung1337@gmail.com \
    --cc=peterx@redhat.com \
    --cc=peterz@infradead.org \
    --cc=posk@google.com \
    --cc=punit.agrawal@bytedance.com \
    --cc=rientjes@google.com \
    --cc=rppt@kernel.org \
    --cc=shakeelb@google.com \
    --cc=soheil@google.com \
    --cc=songliubraving@fb.com \
    --cc=tatashin@google.com \
    --cc=vbabka@suse.cz \
    --cc=will@kernel.org \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).